SOURCE-LINKED INTELLIGENCE

TopoCompress: Long Context Compression via Graph-Wired Semantic Trajectories

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Long-context compression is essential for reducing the cost and latency of large language model inference. However, existing methods can fragment important evidence, require additional training or alignment, and often depend on the target model for effective compression. We introduce TopoCompress, a training-free and model-agnostic framework that compresses long contexts by selecting coherent semantic spans. TopoCompress first scores each span using dense and lexical query relevance together with semantic acceleration. It then constructs a hybrid graph that connects spans based on semantic sim

Read original source ↗ Open in workspace

recordType

paper

region

Global